super-dev CLAUDE.md

super-dev CLAUDE.md is an instructions file for coding agents from shangyankeji/super-dev. It costs 3,366 tokens per session, scanned A, original, MIT.

A repository guide for Claude Code, an AI coding assistant, explaining a Python command-line project and its development commands.

In plain words
What is it for?
Use it when working on this Python project, especially to install it, run its command-line tool, format and check code, or run tests.
Why use it?
It gives the assistant and developers a shared reference for how the project is organised, installed, checked, and tested.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/shangyankeji/super-dev/claude-md
Clone the repo
git clone --depth 1 https://github.com/shangyankeji/super-dev

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for super-dev CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shangyankeji/super-dev/claude-md.svg)](https://agentmods.dev/instructions/shangyankeji/super-dev/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shangyankeji/super-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/shangyankeji/super-dev/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,366 This file is loaded in full into every session.
When invoked 3,366 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.03366 $0.03366
Opus 5 $0.01683 $0.01683
Sonnet 5 $0.00673 $0.00673
Haiku 4.5 $0.00337 $0.00337

Measured 5d ago against content hash 9cae499efca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

super-dev CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Super Dev is a Python CLI tool (v2.4.0) that orchestrates AI-driven development pipelines inside host environments (e.g., Claude Code). It provides governance, quality gates, and audit artifacts for commercial-grade software delivery. It is NOT an independent AI agent — it's a governance layer that runs inside a host's coding environment.

Build & Development Commands

# Install in development mode (requires Python 3.10+)
pip install -e ".[dev]"

# Run the CLI
super-dev

# Linting & formatting
ruff check super_dev/              # lint
ruff check --fix super_dev/        # auto-fix lint issues
black super_dev/ --check           # check formatting
black super_dev/                   # apply formatting

# Type checking
mypy super_dev/

# Run all tests
pytest

# Run a single test file
pytest tests/unit/test_workflow.py

# Run a specific test
pytest tests/unit/test_workflow.py::test_function_name -v

# Run with coverage
pytest --cov=super_dev

Code Style

  • Line length: 100 (configured in both ruff and black)
  • Target Python: 3.10+
  • Ruff rules: E, F, I, N, W, UP (E501 ignored)
  • All imports must be sorted (ruff I rule)

Architecture

Core Pipeline (super_dev/)

The CLI entry point is super_dev/cli.py (~6k lines), built as a large class composed via mixins:

  • cli_parser_mixin.py — argparse command definitions
  • cli_analysis_mixin.py — analysis subcommands
  • cli_governance_mixin.py — governance/enforcement subcommands
  • cli_host_ops_mixin.py — host tool operations
  • cli_experience_mixin.py — UX enhancements
  • cli_deploy_runtime_mixin.py — deployment/runtime commands
  • cli_release_quality_mixin.py — release & quality commands
  • cli_spec_mixin.py — spec management commands

Pipeline Orchestration (super_dev/orchestrator/)

  • engine.py — main pipeline engine driving phase transitions
  • governance.py — governance policy enforcement during pipeline
  • knowledge.py / knowledge_pusher.py — knowledge injection into pipeline stages
  • quality.py — quality gate evaluation
  • contracts.py — pipeline contract definitions

Read the full file on GitHub · 272 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 272 lines · 3,366 tokens per session scan A 9cae499efca6

Subscribe to this mod's changes

super-dev CLAUDE.md is an instructions file published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 3,366 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories